AutoNLP Preview: Auto model-selection, fine-tuning and deployment of state-of-the-art NLP models Abhishek Thakur 2026-09-28 | AutoNLP Preview: Auto model-selection, fine-tuning and deployment of state-of-the-art NLP models
Arcee Conductor: Intelligent Model Routing ($200 free credits!) Abhishek Thakur 2025-03-17 | 🚀 I'm thrilled to announce the launch of Arcee Conductor, a game-changing platform that's about to revolutionize the way you interact with AI models! 🤖 As the pioneers of small language models (SLMs), we've been working tirelessly to bring you the most exciting innovation in the AI space.Here's a quick TL;DR of what Arcee Conductor is all about: 🌟 Choice and flexibility: Get access to multiple models, including our powerful SLMs and third-party LLMs, to choose the best one for your specific use case🤖 Intelligent routing: Our platform evaluates which model is best-suited for each of your queries, ensuring you get the most accurate results📈 Cost savings: Reduce your AI costs with our affordable SLMs, while still having access to leading LLMs when needed🚀 Easy to get started: Sign up now and try Arcee Conductor today, with 400 million tokens (a $200 value) on us! 🎁📊 Proven track record: Our SLMs have already racked up 222K+ downloads on Hugging Face, with customers seeing significant cost savings and improved accuracyFor a limited time, you can get $200 credits to use with Conductor for FREE. Check it out here: conductor.arcee.aiPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
BARK: Free Text to Speech & Voice Cloning Abhishek Thakur 2023-08-01 | In this video, I'm going to show you how to generate awesome voices for FREE using BARK! In addition, I will also show you how you can clone any voice with just one sample of 10-15 seconds!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Build your own Stable Doodle: Sketch to Image Abhishek Thakur 2023-07-28 | In this video, I'll show you how to create an app for sketch to image. We will be using everything from UniControl paper and change a few things and add stable diffusion xl refiner to create a sketch to image tool.You can play with the app here: huggingface.co/spaces/abhishek/sketch-to-imagePlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Stable Diffusion XL (SDXL) DreamBooth: Easy, Fast & Free | Beginner Friendly Abhishek Thakur 2023-07-26 | In this video, I'll show you how to train amazing dreambooth models with the newly released SDXL 1.0! In addition to that, we will also learn how to generate images using SDXL base model and the use of refiner to enhance the quality of generated images.The commands used for training in this video are as follows:!pip install -U autotrain-advanced!autotrain setup --update-torch!autotrain dreambooth \--model stabilityai/stable-diffusion-xl-base-1.0 \--output output/ \--image-path images/ \--prompt "photo of sks dog" \--resolution 1024 \--batch-size 1 \--num-steps 500 \--fp16 \--gradient-accumulation 4 \--lr 1e-4On google colab, you can add --use-8bit-adam parameter and change resolution to 512 if you are on free version of google colab.Inference code: Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
The FASTEST way to build CHAT UI for LLAMA-v2 Abhishek Thakur 2023-07-22 | In this video, ill show you the fastest way of building a chatbot user interface (chat ui)! We will be using gradio.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
The EASIEST way to finetune LLAMA-v2 on local machine! Abhishek Thakur 2023-07-20 | In this video, I'll show you the easiest, simplest and fastest way to fine tune llama-v2 on your local machine for a custom dataset! You can also use the tutorial to train/finetune any other Large Language Model (LLM). In this tutorial, we will be using autotrain-advanced.AutoTrain Advanced github repo: github.com/huggingface/autotrain-advancedSteps:Install autotrain-advanced using pip:- pip install autotrain-advancedSetup (optional, required on google colab):- autotrain setup --update-torchTrain:autotrain llm --train --project_name my-llm --model meta-llama/Llama-2-7b-hf --data_path . --use_peft --use_int4 --learning_rate 2e-4 --train_batch_size 12 --num_train_epochs 3 --trainer sftIf you are on free version of colab, use this model instead: huggingface.co/abhishek/llama-2-7b-hf-small-shards. This is a smaller sharded version of llama-2-7b-hf by meta.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Run LLAMA-v2 chat locally Abhishek Thakur 2023-07-19 | In this video, I'll show you how you can run llama-v2 13b locally on an ubuntu machine and also on a m1/m2 mac. We will be using llama.cpp for this video.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
1-Click LLM Deployment! Abhishek Thakur 2023-07-17 | In this video, I show you how you can deploy large language models (LLMs) in just one click using Hugging Face's Inference Endpoints! The content of this video can be used both for personal and professional/enterprise usage!Inference Endpoints Docs: huggingface.co/docs/inference-endpoints/indexPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
100% Private & Local PDF ChatBot (without langchain) Abhishek Thakur 2023-07-16 | In this video, I'll show you how to create your own PDF chatbot without depending on libraries that have way too much abstraction. The Bot created this way not only ensures that your data is private but also makes sure that you control each and every aspect of the bot, including all kinds of preprocessing, top results, search, etc. We will be using two different models: falcon-7b and falcon-40b!Code: gist.github.com/abhishekkrthakur/401c39d422fb6beff1600effe81f498aPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Deploy FULLY PRIVATE & FAST LLM Chatbots! (Local + Production) Abhishek Thakur 2023-07-14 | In this video, I'll show you how you can deploy and run large language model (LLM) chatbots locally. The steps followed are also valid for production environment and the tutorial is also production ready! By the end of the tutorial, you will be running an LLM like Falcon-7B (or 40B or any LLM) locally and you would have also deployed a chat interface to use the local llm and chat with it!For the video, we will be using text-generation-inference: github.com/huggingface/text-generation-inferenceAnd chat-ui: github.com/huggingface/chat-uiPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Train LLMs in just 50 lines of code! Abhishek Thakur 2023-07-12 | In this video, i'll show you how you can train or finetune your own LLM in the least amount of code possible. In addition, as a bonus, ill also show you how you can do the same without writing any code at all.For the coding part, we will be using torch, transformers, peft and trl libraries.For the no-code solution, we will be using autotrain-advanced. You can install autotrain-advanced using pip: "pip install autotrain-advanced"I'll be using my home machine. No cloud needed!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Content Based Image Search: InstructBLIP + Sentence Transformers + FAISS Abhishek Thakur 2023-07-09 | In this video, we create a system for content based image search using instruct blip, sentence transformers and faiss. In the end, we have built a system to search for images just by using text and we can even search for intricate details!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Building a summarizer using XGen-7b: Fully open source LLM by Salesforce Abhishek Thakur 2023-06-29 | In this video, we will use XGen, the recently announced, Apache 2.0 LLM by Salesforce to create a summarization application. Check out the announcement blog post here: blog.salesforceairesearch.com/xgenPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
How to: AI Generated QR Codes (Using Python) Abhishek Thakur 2023-06-27 | In this video, I will show you how to generate awesome QR codes using Hugging Face's Diffusers library. We will be using Stable Diffusion with ControlNet!Check out the Gradio demo here: huggingface.co/spaces/huggingface-projects/QR-code-AI-art-generatorPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Movie Genre Prediction Abhishek Thakur 2023-06-11 | In this video, we will take a look at the latest competition on Hugging Face: Movie Genre Prediction.The competition is organized by Data Driven Science (datadrivenscience.com)Competition link: huggingface.co/spaces/competitions/movie-genre-predictionPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Finetune LLMs (llama, vicuna, gptneo, pythia) without any code! Abhishek Thakur 2023-05-15 | In this video, ill show you how anyone can finetune LLMs like llama, vicuna, gptneo, pythia, etc without writing a single line of code! Check out AutoTrain's documentation here: hf.co/docs/autotrainPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
🤗 AutoTrain: Train state-of-the-art image classification models (no code) Abhishek Thakur 2023-04-14 | In this video, I show you how you can train state of the art image classification models without writing a single line of code! We will be using AutoTrain Advanced from Hugging Face: huggingface.co/spaces/autotrain-projects/autotrain-advanced#huggingface #nocode #autotrain---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Custom object detection in Python using YOLOv8 Abhishek Thakur 2023-04-12 | In this video, I discuss the YOLOv8 data format and how to train a custom object detection model using Ultralytics YOLOv8. Please note that I will be using the Python API and not the CLI. We will be detecting litter in images of water bodies!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Segment Anything + ControlNet + Stable Diffusion = 💥 Abhishek Thakur 2023-04-11 | Hugging Face Space: huggingface.co/spaces/abhishek/StableSAMPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Stable Diffusion Inpainting with Segment Anything Model (SAM) Abhishek Thakur 2023-04-10 | In this video, I combine the output of Segment Anything Model (SAM) by Meta AI with Stable Diffusion Inpainting using Hugging Face Diffusers library and Gradio. In the end, we create a simple app for inpainting in which mask is decided by the SAM model.Demo link will be pasted here when its availableExample image comes from here: github.com/CompVis/latent-diffusion/blob/main/data/inpainting_examples/6458524847_2f4c361183_k.png#stablediffusion #samPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
How to create GPT-powered conversational bot for any website Abhishek Thakur 2023-04-09 | In this video, I will show you a simple but effective way to create a GPT-powered conversational bot for any website. We will be using scrapy, langchain and openai's api.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)#gpt #chatgpt #pythonMy book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
iOS app for stable diffusion with zero knowledge of iOS app development Abhishek Thakur 2023-04-02 | I built an ios app for diffuzers (github.com/abhishekkrthakur/diffuzers) using only AI tools with ZERO knowledge of how to create iOS apps! All I used was xcode and chatgpt!#shorts Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
TS-11: Transfer learning for time series Abhishek Thakur 2022-10-12 | Notebook: kaggle.com/code/konradb/ts-11-deep-learning-for-ts-transfer-learning Transfer learning is a research problem in ML that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. IT has enabled progress in areas with limited data availability in both CV and NLP domains. Several modern applications of machine learning are built around TL, so it's only natural that people would start thinking about using this approach to time series: while less obvious to formulate (what does it mean to learn time series features across domains), the idea of transfer learning for time series has huge potential. In this notebook we explore the idea in some more detail.
How to become a data scientist in 30 days? Abhishek Thakur 2022-10-06 | How to become a data scientist in 30 days?.......The secret is to stop watching these kinds of videos and start learning and doing.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
TS-10: Validation methods for time series Abhishek Thakur 2022-09-21 | Notebook: kaggle.com/code/konradb/ts-10-validation-methods-for-time-series Every ML practitioner knows that validation matters: while it is common knowledge for classification and regression models, time series models have received less attention on that front. In this episode we will walk through different manners of assessing performance of time series models without breaking the arrow of time.
TS-9: Hybrid methods for time series Abhishek Thakur 2022-09-07 | Code: kaggle.com/code/konradb/ts-9-hybrid-methods Abstract: Time series analysis has both vintage approaches (like ARIMA) and modern ones (LSTM). Over time, many people started mixing the two just to see what would happen - in this umbrella episode we will look at three examples of such hybrid models.
TS-8: Hierarchical Time Series Abhishek Thakur 2022-07-28 | Hierarchical structures are all around us: at work, at home, in sports, in Jordan Peterson lectures - and most interestingly from the point of view of this talk, in time series data. Whether you are dealing with supply chain, sales or tourism (or other examples that escape me), your time series is likely to have some sort of hierarchical structure that can be exploited for predicting the future more accurately. In this episode we will talk about the different methods for reconciliation of hierarchical time series: combining the forecasts at different levels of aggregation in a consistent and efficient manner. Notebook: kaggle.com/code/konradb/ts-8-hierarchical-time-series
TS-7: Survival analysis Abhishek Thakur 2022-07-22 | Survival analysis should be a part of the toolbox of every data scientist - but unless you work in clinical research, it probably isn't. It originated in medical statistics (which is kind of evident from terminology), but the applications are way broader. In this episode we talk about when and why you should consider using survival analysis and show how to apply to different problems - including churn and customer lifetime value. v2
Data representations for neural networks Abhishek Thakur 2022-05-31 | This is a video in the Python Deep Learning series which is a book by François Chollet. Deep Learning with Python (2nd Edition, by Francois Chollet). If you don't have the book, you can buy it here: bit.ly/keras2nd. In this video, talk about tensors, ranks, scalers, and vectors, and look at different data types for deep learning.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
My First Neural Network using Keras Abhishek Thakur 2022-05-30 | This is a video in the Python Deep Learning series which is a book by François Chollet. Deep Learning with Python (2nd Edition, by Francois Chollet). If you don't have the book, you can buy it here: bit.ly/keras2nd. In this video, we will be building our very first neural network on the MNIST dataset using Keras.Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
TS-6: Deep learning for time series - sequences Abhishek Thakur 2022-05-27 | Abstract: Time series are, first and foremost, sequences - so it's only natural to apply sequence modeling approach from deep learning to such problems. In this episode we present the vintage DL methods (RNN, GRU and LSTM) and show their applications for single- and multistep forecasting. We also take time to explore the connection RNN have to curve fitting - via the ES-RNN model.
What is deep learning? Abhishek Thakur 2022-05-23 | This is a video in the Python Deep Learning series which is a book by François Chollet. Deep Learning with Python (2nd Edition, by Francois Chollet). If you don't have the book, you can buy it here: bit.ly/keras2ndJoin MLSpace Discord for discussions: discord.gg/sb9HFZwKMRPlease subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Kaggle Hidden Gems - The Competition (with Heads or Tails) Abhishek Thakur 2022-04-14 | The Kaggle platform is a treasure trove for numerous data science & machine learning notebooks. The Hidden Gems series attempts to highlight underrated notebooks of high quality. To celebrate the 100th episode of Hidden Gems, we are hosting a Notebooks competition aimed at crafting insightful notebooks with engaging narration. We will talk all about the competition, what makes a great notebook, and how to win cool prizes by participating. Check out the competition here: kaggle.com/datasets/headsortails/notebooks-of-the-week-hidden-gems/discussion/317098
TS-5: Automatic for the people Abhishek Thakur 2022-04-13 | Abstract: In this episode we focus on the idea of a one stop shop for time series analysis: in the last few years, several packages have appeared that position themselves in such a fashion.We will take them for a test drive and have a look at how close they come to fulfilling the promise.
TS-4: Sales and demand forecasting Abhishek Thakur 2022-03-30 | Abstract: This episode focuses on a popular business forecasting problem – predicting sales and demand. As with every topic, there are some specific challenges here – the most important one being the intermittent nature of the data: our time series frequently have long periods of inactivity (zero values), when vintage methods struggle. We will talk about how to handle such situation both for a single series, as well as jointly analysing multiple ones.
TS-3: Time series models for finance Abhishek Thakur 2022-03-05 | Time series encountered in finance come with some characteristics that make them stand out compared to other applications, with volatility clustering being the most prominent one. In this episode, we will talk about GARCH models and some of their applications - like Value at Risk calculation.
TS-2: ARIMA and Friends Abhishek Thakur 2022-02-19 | ARIMA are the linear models of the time series world. Historically, they were the workhorses of time series analysis - for many people meant just finding right order of such model. In this episode, we will demonstrate how this vintage approach remains competitive in 2022, as well as a useful element in your toolkit.
TS-1: Curve fitting is (almost) all you need Abhishek Thakur 2022-02-05 | In this first tutorial on time series analysis, we will discuss the basic methods that require no actual statistics - the classic (exponential smoothing) and the modern (Prophet). By learning these techniques, you can quickly reach a level that allows you to gain insights, interpret what's going on and deliver quality forecasts for actual real-life datasets.
Making Transformers go brum, brum, brum 🏎 (with Lewis Tunstall) Abhishek Thakur 2022-01-31 | Since their introduction in 2017, Transformers have rapidly become the state-of-the-art approach to model tasks in NLP, computer vision, and audio, However, in many situations, accuracy is not enough — your fancy model isn’t very useful if it’s too slow or large to meet the business requirements of your application. In this talk, Lewis will discuss various techniques you can use to optimize Transformer models for production environments. He will cover knowledge distillation and weight quantization, as well as frameworks like ONNX Runtime. This talk is based on a chapter from the upcoming O’“Reilly book on “Natural Language Processing with Transformers” — we’ll be giving away 5 copies of the book as part of this event!
Handling Missing Values (with Rob Mulla) Abhishek Thakur 2022-01-24 | In this tutorial, we will know all about handling missing values in tabular data. This video is part of the applied ml competition series. If you want to join the song popularity prediction competition, join by clicking this link: kaggle.com/t/df24a2b9ddc94bbcad6badeacab7f1f5
Song Popularity Prediction: EDA with Martin Henze (Part-2) Abhishek Thakur 2022-01-21 | This is part-2 of EDA with Martin Henze (kaggle.com/headsortails). If you want to take part in the competition, use this invite link: kaggle.com/t/df24a2b9ddc94bbcad6badeacab7f1f5
Song Popularity Prediction EDA with Martin Henze (Heads or Tails) Abhishek Thakur 2022-01-19 | In this video, Martin Henze and I will discuss some basic EDA for the new applied machine learning beginner competition on Kaggle by MLSpace. You can join the competition by clicking on this link: kaggle.com/t/df24a2b9ddc94bbcad6badeacab7f1f5
Talks S2E7 (Konrad Banachewicz): Time Series Analysis - Vintage Toolkit For Modern Times Abhishek Thakur 2021-09-25 | Abstract : An overview of time series methods - from classics to modern ones - and how you can use them in practice; from power consumption to sales data, multiple seasonalities to almost random, there is something in the time series toolkit that will come in handy. Speaker Bio: After finishing his PhD in statistics, Konrad has been crunching numbers for a living for years and have dabbled in just about everything along the way (credit risk analysis, trading commodities, predictive maintenance). These days he leads the central data science team at eClassifiedsGroup (part of Adevinta), where they optimize the e-commerce experience so people actually get what they need, and not merely what they clicked upon---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishekInstagram: instagram.com/abhi1thakur
Talks S2E6 (Louise Ferbach): Deep Learning For Survival Analysis Abhishek Thakur 2021-09-17 | Abstract : A review of the most common deep learning models in survival analysis, and how you can apply them to any time-to-event prediction problem : credit default, machine failure, cancer relapse, etc.Speaker Bio : I studied fundamental mathematics in Paris, and statistics in engineering school. I came across data science by chance, and mostly thanks to Kaggle ! I am currently Kaggle Competitions Master and just starting as Actuary Data Scientist at SCOR. I work on everything statistics-related in the life insurance sector : predicting survival times of cancer patients, etc.---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishekInstagram: instagram.com/abhi1thakur
Talks S2E5 (Luca Massaron): Hacking Bayesian Optimization Abhishek Thakur 2021-09-10 | Title: Hacking Bayesian OptimizationAbstract: working with Scikit-optimize (skopt), we program custom procedures in order to suit complex hyper-parameter setting problems, control for time and cost of computation, extension to neural architecture search.Speaker Bio: Luca Massaron is a Google Developer Expert in machine learning with more than a decade of experience in data science. He is also the author of several best-selling books on AI and a Kaggle master who reached number 7 for his performance in data science competitions.---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishekInstagram: instagram.com/abhi1thakur
Talks S2E4 (Lavanya Shukla): Reproducible machine learning at scale Abhishek Thakur 2021-09-03 | Abstract: How can we support effective, reproducible, and explainable deep learning and coordination across practitioners? In this talk, Lavanya Shukla will share best practices for conducting, debugging, and sharing deep learning experiments at scale. She will talk through how some of the best tech companies in the world use the Weights & Biases platform for managing datasets, debugging models, versioning training/evaluation recipes, extracting insights, and storing all the crucial details needed to make their models reproducible and their research collaborative.Speaker Bio: Lavanya is the Head of Growth at Weights and Biases, an experiment tracking platform for deep learning. She began working on AI 10 years ago when she founded ACM SIGAI at Purdue University as a sophomore. In a past life, she taught herself to code at age 10, and founded the machine learning startup Dataland. You can find her on twitter: @lavanyaai---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)To buy my book, Approaching (Almost) Any Machine Learning problem, please visit: bit.ly/buyaamlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishekInstagram: instagram.com/abhi1thakur
Kaggles 30 Days Of ML (Competition Part-7): What are public and private leaderboard? Abhishek Thakur 2021-08-31 | This video is a walkthrough of Kaggle's #30DaysOfML. In this video, we will know about public and private leaderboards on kaggle and how to choose final submissions.Note: this video is not sponsored by #Kaggle!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Talks S2E3 (Merve Noyan): BYOB - Build Your Own Bot Abhishek Thakur 2021-08-27 | Summary: This workshop will give you a primer on conversational agents and how to make one according to your use case. I will cover frameworks, state-of-the-art in natural language understanding and dialogue management, generative models, what you can and can’t build. I will also cover common mistakes people make during chatbot lifecycle, starting from training data to monitoring the production (e.g. working with synthetic data or not falling back gracefully).Bio: Merve is a Machine Learning Engineer at iamyiam, making chatbots for living. She’s also a Google Developer Expert in Machine Learning and a graduate student in data science. Her main research interests are natural language processing and conversational AI.---Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)To buy my book, Approaching (Almost) Any Machine Learning problem, please visit: bit.ly/buyaamlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishekInstagram: instagram.com/abhi1thakur
Kaggles 30 Days Of ML (Competition Part-6): Model Stacking Abhishek Thakur 2021-08-25 | This video is a walkthrough of Kaggle's #30DaysOfML. In this video, we will learn what model stacking is and how to do it in a proper manner! Check part-5 for model blending!Notebook: Note: this video is not sponsored by #Kaggle!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)To get my book, Approaching (Almost) Any Machine Learning Problem, for free, please visit: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
Kaggles 30 Days Of ML (Competition Part-5): Model Blending 101 Abhishek Thakur 2021-08-24 | This video is a walkthrough of Kaggle's #30DaysOfML. In this video, we will learn what model blending is and how to do it in a proper manner!Notebook: kaggle.com/abhishek/competition-part-5-blending-101Note: this video is not sponsored by #Kaggle!Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)To get my book, Approaching (Almost) Any Machine Learning Problem, for free, please visit: bit.ly/approachingmlFollow me on:Twitter: twitter.com/abhi1thakurLinkedIn: linkedin.com/in/abhi1thakurKaggle: kaggle.com/abhishek
